公开(公告)号：US11468206B2

公开(公告)日：2022-10-11

申请号：US15999553

申请日：2018-08-20

Applicant: SRI International

Inventor： Chih-hung Yeh ,  Karen Myers ,  Mohamed Amer

IPC: G06F30/13 ,  G06N3/04 ,  G06N20/00

Abstract: Techniques are disclosed for using a computation engine executing a machine learning system to generate, according to constraints, renderings of a building or building information modeling (BIM) data for the building, wherein the constraints include at least one of an architectural style or a building constraint. In one example, an input device is configured to receive an input indicating one or more surfaces for the building and one or more constraints. A machine learning system executed by a computation engine is configured to apply a model, trained using images of buildings labeled with corresponding constraints for the buildings, to the one or more surfaces for the building to generate at least one of a rendering of the one or more surfaces for the building according to the constraints or BIM data for the building according to the constraints. Further, the machine learning system is configured to output the rendering or the BIM data.

公开(公告)号：US20200320435A1

公开(公告)日：2020-10-08

申请号：US16842265

申请日：2020-04-07

Applicant: SRI International

Inventor： Pedro Daniel Barbosa Sequeira ,  Melinda T. Gervasio ,  Chih-hung Yeh

IPC: G06N20/00 ,  G06N5/04

Abstract: Techniques are disclosed for applying a multi-level introspection framework to interaction data characterizing a history of interaction of a reinforcement learning agent with an environment. The framework may apply statistical analysis and machine learning methods to interaction data collected during the RL agent's interaction with the environment. The framework may include a first (“environment”) level that analyzes characteristics of one or more tasks to be solved by the RL agent to generate elements, a second (“interaction”) level that analyzes actions of the RL agent when interacting with the environment to generate elements, and a third (“meta-analysis”) level that generates elements by analyzing combinations of elements generated by the first level and elements generated by the second level.

公开(公告)号：US20250013869A1

公开(公告)日：2025-01-09

申请号：US18762333

申请日：2024-07-02

Applicant: SRI International

Inventor： John Cadigan ,  Dayne Brian Freitag ,  John Joseph Niekrasz ,  Chih-hung Yeh

IPC: G06N3/084

Abstract: In an example, a method for a method for training a Machine Learning (ML) model using arbitrarily sized training data files, to selectively identify informative portions of one or more training data files for improving the ML model includes automatically selectively identifying, by a computing system, one or more informative portions of one or more training data files; calculating, by the computing system, gradients for the identified one or more informative portions; and updating, by the computing system, weights of a ML model using the calculated gradients.

公开(公告)号：US20230289498A1

公开(公告)日：2023-09-14

申请号：US17654737

申请日：2022-03-14

Applicant: SRI International ,  OBAYASHI CORPORATION ,  Hypar Inc.

Inventor： Anirban Roy ,  Jihua Huang ,  Sujeong Kim ,  Min Yin ,  Chih-hung Yeh ,  Takuma Nakabayshi ,  Yoshito Tsuji ,  Ian Keough ,  Matthew Campbell

IPC: G06F30/27 ,  G06T3/00 ,  G06V10/764 ,  G06V10/774 ,  G06F30/13

CPC classification number: G06F30/27 ,  G06T3/00 ,  G06V10/764 ,  G06V10/774 ,  G06F30/13

Abstract: In general, the disclosure describes techniques for parameterizing building information using images. In an example, a method includes receiving an image of a building; applying, by a machine learning system, a machine learning model to the received image of a building to generate, for a new building, new building parameters to be input to a building information modeling (BIM) data generation system, wherein the machine learning model is trained using images of buildings and corresponding building parameters for the buildings; and outputting, by the machine learning system, the new building parameters for the new building.

公开(公告)号：US20210142005A1

公开(公告)日：2021-05-13

申请号：US17094278

申请日：2020-11-10

Applicant: SRI International

Inventor： Natarajan Shankar ,  Stephane Graham-Lengrand ,  Daniel Elenius ,  Chih-hung Yeh

IPC: G06F40/211 ,  G06F40/253 ,  G06F40/279 ,  G06N7/00 ,  G06N20/20

Abstract: In general, the disclosure describes techniques for machine learning for translation to structured computer readable representation. An example method to generate a training set for a natural language translation model includes receiving, by a computing system, a grammar comprising rules, one or more of the rules being associated with random biases; generating, by the computing system, at least one of random trees or random graphs based on the random biases in the grammar; for each of the random trees or random graphs, by the computing system, generating a natural language sample; and generating, by the computing system, the training set with the random trees or random graphs and the corresponding natural language samples.

公开(公告)号：US20200057824A1

公开(公告)日：2020-02-20

申请号：US15999553

申请日：2018-08-20

Applicant: SRI International

Inventor： Chih-hung Yeh ,  Karen Myers ,  Mohamed Amer

IPC: G06F17/50 ,  G06N3/04 ,  G06F15/18

Abstract: Techniques are disclosed for using a computation engine executing a machine learning system to generate, according to constraints, renderings of a building or building information modeling (BIM) data for the building, wherein the constraints include at least one of an architectural style or a building constraint. In one example, an input device is configured to receive an input indicating one or more surfaces for the building and one or more constraints. A machine learning system executed by a computation engine is configured to apply a model, trained using images of buildings labeled with corresponding constraints for the buildings, to the one or more surfaces for the building to generate at least one of a rendering of the one or more surfaces for the building according to the constraints or BIM data for the building according to the constraints. Further, the machine learning system is configured to output the rendering or the BIM data.

公开(公告)号：US20230394413A1

公开(公告)日：2023-12-07

申请号：US18330930

申请日：2023-06-07

Applicant: SRI International

Inventor： Subhodev Das ,  Aswin Nadamuni Raghavan ,  Avraham Joshua Ziskind ,  Timothy J. Meo ,  Bhoram Lee ,  Chih-hung Yeh ,  John Cadigan ,  Ali Chaudhry ,  Jonathan C. Balloch

IPC: G06Q10/0637

CPC classification number: G06Q10/06375

Abstract: In general, the disclosure describes techniques for Artificial Intelligence (AI) models that can automatically generate diverse, explainable, interpretable, reactive, and coordinated behaviors for a team. In an example, a method includes receiving multimodal input data within a simulator configured to simulate solving a predefined problem by a team including a plurality of agents; generating one or more generative neural network models based on the multimodal input data and based on a predetermined threshold of success of problem solving in the simulator; outputting, by the one or more generative neural network models, one or more multi-agent controllers, wherein each of the one or more multi-agent controllers comprises recommended behaviors for each of the plurality of agents to solve the predefined problem in a manner that is consistent with the multimodal input data.

公开(公告)号：US11597394B2

公开(公告)日：2023-03-07

申请号：US16222623

申请日：2018-12-17

Applicant: SRI International

Inventor： Chih-hung Yeh ,  Boone Adkins ,  Melinda T. Gervasio ,  Karen L. Myers ,  Rodrigo de Salvo Braz

IPC: G06N20/00 ,  B60W40/09 ,  G05D1/00 ,  G07C5/08 ,  G05D1/02

Abstract: In general, the disclosure describes various aspects of techniques for evaluating decisions determined by autonomous devices. A device comprising a memory and a processor may be configured to perform the techniques. The memory may store first state data representative of a first observational state detected by an autonomous device, and first action data representative of one or more first actions the autonomous device performs responsive to detecting the first observational state. The processor may execute a computation engine configured to identify, based on the first action data, a first inflection point representative of changing behavior of the autonomous device. The computation engine may further be configured to determine, based on the first inflection point, first explanatory data representative of portions of the first state data on which the autonomous device relied that explain the changing behavior of the autonomous device, and output the first explanatory data.

公开(公告)号：US11568246B2

公开(公告)日：2023-01-31

申请号：US16810324

申请日：2020-03-05

Applicant: SRI International

Inventor： Chih-hung Yeh ,  Melinda T. Gervasio ,  Karen L. Myers ,  Daniel J. Sanchez ,  Matthew Crossley

IPC: G06F40/30 ,  G06N3/08 ,  G06N3/04

Abstract: Techniques are disclosed for training a machine learning model to perform actions within an environment. In one example, an input device receives a declarative statement. A computation engine selects, based on the declarative statement, a template that includes a template action performable within the environment. The computation engine generates, based on the template, synthetic training episodes. The computation engine further generates experiential training episodes, each experiential training episode collected by a machine learning model from past actions performed by the machine learning model. Each synthetic training episode and experiential training episode comprises an action and a reward. A machine learning system trains, with the synthetic training episodes and the experiential training episodes, the machine learning model to perform the actions within the environment.